t.wordhist

一个C语言写的快速贝叶斯垃圾邮件过滤工具

#! /bin/sh

# Note:  When run via "make check", test output files are automatically deleted.
#	 When run from the command line, output files are left in directory
#	 wordhist.YYYYMMDD.  This is useful when something is different.
#
#	 ./inputs  - test inputs
#	 ./outputs - known correct outputs
#
#	 wordhist.YYYYMMDD:
#		directory containing individual output files

NODB=1 . ${srcdir=.}/t.frame

[ -d ${TMPDIR}/tests ] && rm -rf ${TMPDIR}/tests
mkdir -p ${TMPDIR}/tests

OUT="${TMPDIR}/wordhist.out"
REF="${TMPDIR}/wordhist.ref"

cat <<EOF >$REF
Histogram
score   count  pct  histogram
0.00     3516 66.30 ################################################
0.05        1  0.02 #
0.10        1  0.02 #
0.15        7  0.13 #
0.20       10  0.19 #
0.25       12  0.23 #
0.30       16  0.30 #
0.35       27  0.51 #
0.40       38  0.72 #
0.45       19  0.36 #
0.50       82  1.55 ##
0.55       10  0.19 #
0.60       29  0.55 #
0.65      135  2.55 ##
0.70        7  0.13 #
0.75       22  0.41 #
0.80       63  1.19 #
0.85       14  0.26 #
0.90       28  0.53 #
0.95     1266 23.87 ##################
tot      5303
hapaxes:  ham    2594 (48.92%), spam     784 (14.78%)
   pure:  ham    3516 (66.30%), spam    1257 (23.70%)
EOF

OPTS="-C -y 0"

$BOGOFILTER $OPTS -s < ${SYSTEST}/inputs/spam.mbx
$BOGOFILTER $OPTS -n < ${SYSTEST}/inputs/good.mbx

$BOGOUTIL -C -H $BOGOFILTER_DIR/wordlist.$DB_EXT >$OUT
$BOGOUTIL -C -d $BOGOFILTER_DIR/wordlist.$DB_EXT >${TMPDIR}/wordlist.txt

if  [ $verbose -eq 0 ]; then
    cmp $REF $OUT
else
    diff $DIFF_BRIEF $REF $OUT
fi